From 293f9caf6514fcf603ad309eda816fb7e5d87946 Mon Sep 17 00:00:00 2001 From: Christian Medina <37550954+cmedinasoriano@users.noreply.github.com> Date: Wed, 1 Jul 2026 16:35:47 -0400 Subject: [PATCH] fix: use correct repo_root path for dataset files --- training/scripts/train.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/training/scripts/train.py b/training/scripts/train.py index b30150a..bc9b21d 100644 --- a/training/scripts/train.py +++ b/training/scripts/train.py @@ -110,8 +110,8 @@ def train(config_path): from datasets import load_dataset import os - # Get dataset paths - assuming run from /home/workdir/artifacts - repo_root = Path(__file__).parent + # Get dataset paths - go up to project root + repo_root = Path(__file__).parent.parent.parent train_path = str(repo_root / "training" / "data" / "train.jsonl") test_path = str(repo_root / "training" / "data" / "test.jsonl") print(f"Looking for dataset at: {train_path}") @@ -206,7 +206,7 @@ def check_setup(config_path): # Check dataset files print("\n3. Dataset files:") - repo_root = Path(__file__).parent + repo_root = Path(__file__).parent.parent.parent # Go up to project root train_path = repo_root / "training" / "data" / "train.jsonl" test_path = repo_root / "training" / "data" / "test.jsonl"